SOURCE-LINKED INTELLIGENCE

LIMODENet: Attention-Free Compact Encoders for Information-Preserving Onboard Satellite Image Restoration

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Onboard satellites must restore a channel-degraded image on a few watts, using neuromorphic accelerators (e.g., BrainChip Akida, Intel Loihi-2) that support no softmax or attention. We ask which encoder restores best under that constraint and introduce LIMODENet (LinearMix-ODENet), a 0.69M softmax-/QKV-free backbone whose residual stages read as ODE discretizations and which is empirically information-preserving (probe accuracy rises 79.9% -> 98.4% from stem to head). At iso-parameters it restores 1 dB DVB-S2X-degraded EuroSAT better than a CNN autoencoder (+1.75 dB PSNR) and a skip-connection

Read original source ↗ Open in workspace

recordType

paper

region

Global